Get live statistics and analysis of Akshay 🚀's profile on X / Twitter

I switched to AI Engineering 2 years ago! It was the best career move I ever made. If you want to start today, here's a roadmap:

Google just dropped a new LLM! You can run it locally on just 0.5 GB RAM. Let's fine-tune this on our own data (100% locally):

How to setup your Claude code project? TL;DR Most developers skip the setup and just start prompting. That's the mistake. A proper Claude Code project lives inside a .𝗰𝗹𝗮𝘂𝗱𝗲/ folder. Start with 𝗖𝗟𝗔𝗨𝗗𝗘.𝗺𝗱 as Claude's instruction manual. Split it into a 𝗿𝘂𝗹𝗲𝘀/ folder as it grows. Add 𝗰𝗼𝗺𝗺𝗮𝗻𝗱𝘀/ for repeatable workflows, 𝘀𝗸𝗶𝗹𝗹𝘀/ for context-triggered automation, and 𝗮𝗴𝗲𝗻𝘁𝘀/ for isolated subagents. Lock down permissions in 𝘀𝗲𝘁𝘁𝗶𝗻𝗴𝘀.𝗷𝘀𝗼𝗻. There are two .𝗰𝗹𝗮𝘂𝗱𝗲/ folders: one committed with your repo, one global at ~/.𝗰𝗹𝗮𝘂𝗱𝗲/ for personal preferences and auto-memory across projects. The .𝗰𝗹𝗮𝘂𝗱𝗲/ folder is infrastructure. Treat it like one. The article below is a complete guide to 𝗖𝗟𝗔𝗨𝗗𝗘.𝗺𝗱, custom commands, skills, agents, and permissions, and how to set them up properly.

I've been coding in Python for 8 years now. ⏳ If I were to start over again in 2023, here's a roadmap: 🧵👇

Harvard university is offering FREE world class education in Data Science! Courses cover: - Python - Data Visualization - Probability - Statistics - Machine Learning - Data Science: Capstone A project-based pedagogy that allows you to learn while building! 🚀 Read more!👇

Bayes’ theorem, clearly explained:

A single 𝗖𝗟𝗔𝗨𝗗𝗘.𝗺𝗱 file just hit 15K GitHub stars. (derived from Karpathy's coding rules) Andrej Karpathy observed that LLMs make the same predictable mistakes when writing code: over-engineering, ignoring existing patterns, and adding dependencies you never asked for. If you've used AI coding assistants, you've hit all of these. But here's the thing: If the mistakes are predictable, you can prevent them with the right instructions. That's exactly what this 𝗖𝗟𝗔𝗨𝗗𝗘.𝗺𝗱 does. You drop one markdown file into your repo, and it gives Claude Code a structured set of behavioral guidelines for your entire project. This is a big deal. - Built entirely around prompt engineering for AI coding assistants - No framework, no complex tooling, just one .md file that shapes behavior Developers are moving past "use AI to write code" and into "engineer the AI's behavior so the code is actually good." The Claude Code ecosystem is growing fast, and the best tools in it aren't always software. Sometimes they're just well-crafted instructions. 100% open-source. I've shared a link to the GitHub repo in the next tweet!

Become a Microsoft Certified Data Analyst🧑‍🎓 Thread 🧵👇

Web scraping will never be the same. (100% open-source visual search at scale) PixelRAG is a retrieval system that skips HTML parsing completely. Instead of scraping a page into text and embedding chunks, it screenshots the page and retrieves the image. A vision-language model reads the answer straight off the pixels. Why that matters: parsing is where web RAG quietly loses information. - A single HTML-to-text parser can drop 40%+ of a page. - Tables, charts, and layout get flattened or thrown out. - Swapping parsers alone can move accuracy ~10 points on the same docs. PixelRAG indexes the page a person actually sees. The team built a visual index of all of Wikipedia, 30M+ screenshots, and it still beats the strongest text RAG baseline by 18.1% on text-only QA. The repo also ships a Claude Code plugin that gives Claude eyes. It lets Claude screenshot any URL and read the rendered page instead of scraping the DOM. So you can hand it a live page, an arXiv paper, or your local site and ask what it actually looks like. One setup script. No MCP server, no backend. How the pipeline works: - Renders each document (web, PDF, image) to image tiles. - Embeds them with Qwen3-VL-Embedding, LoRA fine-tuned on screenshots. - Builds a FAISS index and serves a search API. A stronger reader model lifts accuracy with no re-indexing, since the index is just pixels. Everything is open-source under Apache-2.0. GitHub repo: https://t.co/qun9TjAdmw Talking about RAG, I recently wrote an article on a new approach that makes retrieval much more efficient by cutting corpus size by 40x, reducing tokens per query by 3x, and improving vector search relevance by 2.3x. The article is quoted below.

How LLMs work, clearly explained:

Google just dropped "Attention is all you need (V2)" This paper could solve AI's biggest problem: Catastrophic forgetting. When AI models learn something new, they tend to forget what they previously learned. Humans don't work this way, and now Google Research has a solution. Nested Learning. This is a new machine learning paradigm that treats models as a system of interconnected optimization problems running at different speeds - just like how our brain processes information. Here's why this matters: LLMs don't learn from experiences; they remain limited to what they learned during training. They can't learn or improve over time without losing previous knowledge. Nested Learning changes this by viewing the model's architecture and training algorithm as the same thing - just different "levels" of optimization. The paper introduces Hope, a proof-of-concept architecture that demonstrates this approach: ↳ Hope outperforms modern recurrent models on language modeling tasks ↳ It handles long-context memory better than state-of-the-art models ↳ It achieves this through "continuum memory systems" that update at different frequencies This is similar to how our brain manages short-term and long-term memory simultaneously. We might finally be closing the gap between AI and the human brain's ability to continually learn. I've shared link to the paper in the next tweet!

I recently landed my job as an AI Engineer! Here's a roadmap for those starting today:

100k is not far!! ✨ And we are back with a giveaway! 🙌 To make it extra special, in addition to the books, my favorite keyboard, the Logitech MX Keys is also up for grabs! 🔥 I'll be giving 7 followers the item of their choice!! 📚 This is how you can participate: 1. Like

Google just dropped "Attention is all you need (V2)" This paper could solve AI's biggest problem: Catastrophic forgetting. When AI models learn something new, they tend to forget what they previously learned. Humans don't work this way, and now Google Research has a solution. Nested Learning. This is a new machine learning paradigm that treats models as a system of interconnected optimization problems running at different speeds - just like how our brain processes information. Here's why this matters: LLMs don't learn from experiences; they remain limited to what they learned during training. They can't learn or improve over time without losing previous knowledge. Nested Learning changes this by viewing the model's architecture and training algorithm as the same thing - just different "levels" of optimization. The paper introduces Hope, a proof-of-concept architecture that demonstrates this approach: ↳ Hope outperforms modern recurrent models on language modeling tasks ↳ It handles long-context memory better than state-of-the-art models ↳ It achieves this through "continuum memory systems" that update at different frequencies This is similar to how our brain manages short-term and long-term memory simultaneously. We might finally be closing the gap between AI and the human brain's ability to continually learn. I've shared link to the paper in the next tweet!

I switched to AI Engineering 2 years ago! It was the best career move I ever made. If you want to start today, here's a roadmap:

How to setup your Claude code project? TL;DR Most developers skip the setup and just start prompting. That's the mistake. A proper Claude Code project lives inside a .𝗰𝗹𝗮𝘂𝗱𝗲/ folder. Start with 𝗖𝗟𝗔𝗨𝗗𝗘.𝗺𝗱 as Claude's instruction manual. Split it into a 𝗿𝘂𝗹𝗲𝘀/ folder as it grows. Add 𝗰𝗼𝗺𝗺𝗮𝗻𝗱𝘀/ for repeatable workflows, 𝘀𝗸𝗶𝗹𝗹𝘀/ for context-triggered automation, and 𝗮𝗴𝗲𝗻𝘁𝘀/ for isolated subagents. Lock down permissions in 𝘀𝗲𝘁𝘁𝗶𝗻𝗴𝘀.𝗷𝘀𝗼𝗻. There are two .𝗰𝗹𝗮𝘂𝗱𝗲/ folders: one committed with your repo, one global at ~/.𝗰𝗹𝗮𝘂𝗱𝗲/ for personal preferences and auto-memory across projects. The .𝗰𝗹𝗮𝘂𝗱𝗲/ folder is infrastructure. Treat it like one. The article below is a complete guide to 𝗖𝗟𝗔𝗨𝗗𝗘.𝗺𝗱, custom commands, skills, agents, and permissions, and how to set them up properly.

Blessed with a baby boy! ❤️

20k is not far!! ✨ As a token of gratitude, I'll be giving 3 followers a book of their choice!! 📚 This is how you can participate: 1. Like & RT this tweet 2. Comment name of the Book👇

Google just dropped a new LLM! You can run it locally on just 0.5 GB RAM. Let's fine-tune this on our own data (100% locally):

Become a Microsoft Certified Data Analyst🧑‍🎓 Thread 🧵👇

Here's the easiest way to build an MCP server: 1. Use Gitingest to convert the FastMCP repo into LLM-ready text. 2. Download the text file. 3. Upload it to Google AI Studio, specifying the MCP server type. Gemini 2.5 Pro handles the rest!

I have been coding in Python for 8 years now. ⏳ Here's a roadmap to Master Python! 🚀 A Thread 🧵👇

this is huge. ollama is now compatible with the anthropic messages API. which means you can use claude code with open-source models. think about that for a second. the entire claude harness: - the agentic loops - the tool use - the coding workflows all powered by private LLMs running on your own machine.